Can we open the black box of AI?
Open accessThe DOI matches its Crossref record; 5 of the 6 references it cites were found in a registry or an index.
Abstract
Artificial intelligence is everywhere. But before scientists trust it, they first need to understand how machines learn.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“most contemporary AI models operate as black boxes, making their internal processes difficult to comprehend (Castelvecchi 2016).”
From Artificial intelligence for literature reviews: opportunities and challenges (2024) · cites this paper as Castelvecchi 2016
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The latter space comprises hundreds of layers and millions of parameters, which makes DNNs be considered as complex black-box models [4].”
From Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI (2020) · cites this paper as [4]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Lastly, a prominent concern of AI models based on neural network architecture is their often criticized lack of interpretability which earned them the term ‘black boxes’27,28.”
From Large language models and multimodal foundation models for precision oncology (2024) · cites this paper as [27]
The cited source says what the claim attributes to it.
In the citing paper
“Most of these discussions point to the fact that algorithmic decision-making is often difficult to understand for - and explain to - human agents, due to the different, and sometimes inscrutable for persons, ways of AI operations: the so-called 'black box' problem (Castelvecchi, 2016).”
From Four Responsibility Gaps with Artificial Intelligence: Why they Matter and How to Address them (2021) · cites this paper as Castelvecchi, 2016
The cited source says what the claim attributes to it.
In the citing paper
“Not being able to understand what has been captured by the model [4] and stored in its internal representation may entail a privacy breach.”
From Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI (2020) · cites this paper as [4]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Advances in neural information processing systems 7
Cios, K., & Shields, M. (1997) · Neurocomputing · doi:10.1016/s0925-2312(97)90018-7 · Cited by 22,059
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
Distilling Free-Form Natural Laws from Experimental Data
Schmidt, M., & Lipson, H. (2009) · Science · doi:10.1126/science.1165893 · Cited by 2,890
Probabilistic machine learning and artificial intelligence
Ghahramani, Z. (2015) · Nature · doi:10.1038/nature14541 · Cited by 1,995
Cited by
Items 1,001–1,006 of 1,006
Kučević, E., Grünewald, F., & Schanz, N. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-76827-9_6 · Cited by 11
Multivariate engineering formulas discovery with knowledge-based neural network
Chen, P.-H., Chen, W., & Fan, J. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13448 · Cited by 7
“However, these models function as “black boxes” (Castelvecchi, 2016), limiting the physical interpretation of their outputs.”
Huang, Y., Zhang, H., Ma, B., Yu, Z., Dai, S., Cheng, L., Su, L., Yang, G., & Ma, Q. (2026) · NeuroImage · doi:10.1016/j.neuroimage.2026.121754 · Cited by 5
Lee, R. Y., Uyeda, A. M., Li, K. S., Sibley, J., Cohen, T., Lober, W. B., Dotolo, D. G., Engelberg, R. A., & Kross, E. K. (2025) · Journal of Palliative Medicine · doi:10.1089/jpm.2024.0496 · Cited by 3
“28 – 31 Given the plummeting explainability of more modern NLP models — which are often described as a “ black box, ” 31 and have even been known to confabulate responses 32 — it is tempting for clinical researchers to turn toward simpler, more explainable models such as those based on prede fi ned…”
Moudgalya, S. K., Palileo, C., Patil, S., Linder, R., & Swaminathan, S. (2025) · Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 1 · doi:10.1145/3641554.3701898 · Cited by 3
“Firstly, the “black box" nature of AI systems, characterized by their lack of transparency, is a challenge even for scientists [10, 27].”
Nonlinear transformation of probabilities by large language models
Hintze, A., Bisht, C., Schossau, J., & Hertwig, R. (2025) · Computers in Human Behavior: Artificial Humans · doi:10.1016/j.chbah.2025.100227 · Cited by 1
Metadata
- Authors
- Castelvecchi, D.
- Corresponding author
- Castelvecchi, Davide
- Venue
- Nature
- Published
- 2016-10
- Volume
- 538
- Issue
- 7623
- Pages
- 20-23
- ISSN
- 0028-0836 (ISSN-L)
- 1476-4687
- OpenAlex
- W2528491735
- Cited by
- 1,773
- References
- 6
- Citations by year
- 2026: 195 · 2025: 322 · 2024: 276 · 2023: 244 · 2022: 217 · 2021: 214 · 2020: 148 · 2019: 84 · 2018: 54 · 2017: 18 · 2016: 1
- FWCI
- 42.56
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by-sa
- www.springer.com/tdm (tdm)
- Locations
- Nature (publishedVersion, cc-by-sa)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- artificial intelligence, machine learning, interpretability, explainability, trust in AI
- MeSH terms
- Machine Learning, Astronomy, Creativity, Humans, Physics, Robotics, Thinking, Neural Networks, Computer, Uncertainty, Datasets as Topic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.